Differential influence of habit components on problematic behaviors - Revision 1
Author
Lavinia Wuensch, Yoann Stussi, Théo Vernede, Eva R. Pool
Published
May 20, 2025
Setup
Environment
Testing specific hypotheses with regression
Additional hierarchical multiple regressions conducted to address Reviewer 2’s comments. This analysis was presented in the rebuttal but is not present in the article.
Experiment 1
Media
# Model without habitmodel_exp1_media <-lm(Media ~ Impuls. + Stress + Eat + Comp., data = experiment_1_factors)summary(model_exp1_media)
Call:
lm(formula = Media ~ Impuls. + Stress + Eat + Comp., data = experiment_1_factors)
Residuals:
Min 1Q Median 3Q Max
-2.34509 -0.60489 -0.04435 0.58343 2.53391
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.00560 0.04751 0.118 0.90623
Impuls. 0.13928 0.04915 2.834 0.00486 **
Stress 0.34353 0.05582 6.154 2.02e-09 ***
Eat -0.11357 0.05248 -2.164 0.03112 *
Comp. 0.13364 0.05342 2.502 0.01280 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.9062 on 359 degrees of freedom
(17 observations deleted due to missingness)
Multiple R-squared: 0.1786, Adjusted R-squared: 0.1695
F-statistic: 19.52 on 4 and 359 DF, p-value: 1.51e-14
# Model with habitmodel_exp1_media_habit <-lm(Media ~ Impuls. + Stress + Eat + Comp. + Automaticity + Routine, data = experiment_1_factors)summary(model_exp1_media_habit)
Call:
lm(formula = Media ~ Impuls. + Stress + Eat + Comp. + Automaticity +
Routine, data = experiment_1_factors)
Residuals:
Min 1Q Median 3Q Max
-2.40968 -0.57900 -0.03964 0.54912 2.93490
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.991781 0.314620 -3.152 0.00176 **
Impuls. 0.104430 0.049859 2.095 0.03692 *
Stress 0.299623 0.054824 5.465 8.70e-08 ***
Eat -0.115162 0.050789 -2.267 0.02396 *
Comp. 0.116703 0.054075 2.158 0.03158 *
Automaticity 0.028348 0.005830 4.863 1.74e-06 ***
Routine 0.001909 0.005544 0.344 0.73075
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.8769 on 357 degrees of freedom
(17 observations deleted due to missingness)
Multiple R-squared: 0.2351, Adjusted R-squared: 0.2223
F-statistic: 18.29 on 6 and 357 DF, p-value: < 2.2e-16
# Model comparisonanova(model_exp1_media, model_exp1_media_habit)
Analysis of Variance Table
Model 1: Media ~ Impuls. + Stress + Eat + Comp.
Model 2: Media ~ Impuls. + Stress + Eat + Comp. + Automaticity + Routine
Res.Df RSS Df Sum of Sq F Pr(>F)
1 359 294.81
2 357 274.53 2 20.279 13.185 2.987e-06 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Compulsivity
# Model without habitmodel_exp1_compulsivity <-lm(Comp. ~ Impuls. + Stress + Eat + Media, data = experiment_1_factors)summary(model_exp1_compulsivity)
Call:
lm(formula = Comp. ~ Impuls. + Stress + Eat + Media, data = experiment_1_factors)
Residuals:
Min 1Q Median 3Q Max
-2.25975 -0.63357 -0.09446 0.61354 2.78803
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.002549 0.046538 0.055 0.9564
Impuls. -0.114429 0.048299 -2.369 0.0184 *
Stress 0.307260 0.055157 5.571 4.98e-08 ***
Eat 0.082116 0.051558 1.593 0.1121
Media 0.128232 0.051253 2.502 0.0128 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.8877 on 359 degrees of freedom
(17 observations deleted due to missingness)
Multiple R-squared: 0.1684, Adjusted R-squared: 0.1591
F-statistic: 18.17 on 4 and 359 DF, p-value: 1.317e-13
# Model with habitmodel_exp1_compulsivity_habit <-lm(Comp. ~ Impuls. + Stress + Eat + Media + Automaticity + Routine, data = experiment_1_factors)summary(model_exp1_compulsivity_habit)
Call:
lm(formula = Comp. ~ Impuls. + Stress + Eat + Media + Automaticity +
Routine, data = experiment_1_factors)
Residuals:
Min 1Q Median 3Q Max
-2.00990 -0.63747 -0.07449 0.62052 2.57265
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.379240 0.301458 -4.575 6.57e-06 ***
Impuls. -0.037716 0.048739 -0.774 0.4395
Stress 0.299905 0.053179 5.640 3.47e-08 ***
Eat 0.077639 0.049572 1.566 0.1182
Media 0.110354 0.051133 2.158 0.0316 *
Automaticity -0.006812 0.005843 -1.166 0.2444
Routine 0.029212 0.005166 5.655 3.20e-08 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.8527 on 357 degrees of freedom
(17 observations deleted due to missingness)
Multiple R-squared: 0.2368, Adjusted R-squared: 0.224
F-statistic: 18.46 on 6 and 357 DF, p-value: < 2.2e-16
# Model comparisonanova(model_exp1_compulsivity, model_exp1_compulsivity_habit)
Analysis of Variance Table
Model 1: Comp. ~ Impuls. + Stress + Eat + Media
Model 2: Comp. ~ Impuls. + Stress + Eat + Media + Automaticity + Routine
Res.Df RSS Df Sum of Sq F Pr(>F)
1 359 282.87
2 357 259.59 2 23.277 16.006 2.203e-07 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Experiment 2
Media
# Model without habitmodel_exp2_media <-lm(Media ~ Impuls. + Stress + Eat + Comp., data = experiment_2_factors)summary(model_exp2_media)
Call:
lm(formula = Media ~ Impuls. + Stress + Eat + Comp., data = experiment_2_factors)
Residuals:
Min 1Q Median 3Q Max
-2.29023 -0.59307 -0.01799 0.59344 2.74896
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.157443 0.319999 -3.617 0.000353 ***
Impuls. 0.025876 0.007056 3.667 0.000294 ***
Stress 0.258976 0.063619 4.071 6.1e-05 ***
Eat 0.038292 0.058794 0.651 0.515400
Comp. 0.128939 0.055896 2.307 0.021796 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.8892 on 280 degrees of freedom
Multiple R-squared: 0.2205, Adjusted R-squared: 0.2094
F-statistic: 19.8 on 4 and 280 DF, p-value: 2.281e-14
# Model with habitmodel_exp2_media_habit <-lm(Media ~ Impuls. + Stress + Eat + Comp. + Automaticity + Routine, data = experiment_2_factors)summary(model_exp2_media_habit)
Call:
lm(formula = Media ~ Impuls. + Stress + Eat + Comp. + Automaticity +
Routine, data = experiment_2_factors)
Residuals:
Min 1Q Median 3Q Max
-2.39265 -0.53539 -0.01344 0.54716 2.82893
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.6338757 0.4705081 -3.473 0.000598 ***
Impuls. 0.0171689 0.0072943 2.354 0.019283 *
Stress 0.2279122 0.0626938 3.635 0.000331 ***
Eat 0.0014625 0.0577898 0.025 0.979828
Comp. 0.1291316 0.0551789 2.340 0.019979 *
Automaticity 0.0260938 0.0064656 4.036 7.04e-05 ***
Routine 0.0009244 0.0060943 0.152 0.879547
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.8642 on 278 degrees of freedom
Multiple R-squared: 0.2689, Adjusted R-squared: 0.2531
F-statistic: 17.04 on 6 and 278 DF, p-value: < 2.2e-16
# Model comparisonanova(model_exp2_media, model_exp2_media_habit)
Analysis of Variance Table
Model 1: Media ~ Impuls. + Stress + Eat + Comp.
Model 2: Media ~ Impuls. + Stress + Eat + Comp. + Automaticity + Routine
Res.Df RSS Df Sum of Sq F Pr(>F)
1 280 221.38
2 278 207.64 2 13.737 9.1959 0.0001358 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Compulsivity
# Model without habitmodel_exp2_compulsivity <-lm(Comp. ~ Impuls. + Stress + Eat + Media, data = experiment_2_factors)summary(model_exp2_compulsivity)
Call:
lm(formula = Comp. ~ Impuls. + Stress + Eat + Media, data = experiment_2_factors)
Residuals:
Min 1Q Median 3Q Max
-2.4672 -0.5758 -0.1459 0.5457 3.2351
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.318174 0.346231 -0.919 0.3589
Impuls. 0.007113 0.007639 0.931 0.3526
Stress 0.215889 0.068137 3.168 0.0017 **
Eat 0.042488 0.062267 0.682 0.4956
Media 0.144643 0.062703 2.307 0.0218 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.9418 on 280 degrees of freedom
Multiple R-squared: 0.1256, Adjusted R-squared: 0.1131
F-statistic: 10.05 on 4 and 280 DF, p-value: 1.292e-07
# Model with habitmodel_exp2_compulsivity_habit <-lm(Comp. ~ Impuls. + Stress + Eat + Media + Automaticity + Routine, data = experiment_2_factors)summary(model_exp2_compulsivity_habit)
Call:
lm(formula = Comp. ~ Impuls. + Stress + Eat + Media + Automaticity +
Routine, data = experiment_2_factors)
Residuals:
Min 1Q Median 3Q Max
-2.3843 -0.6058 -0.1178 0.5795 3.1893
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.266269 0.511711 -2.475 0.01394 *
Impuls. 0.012423 0.007894 1.574 0.11669
Stress 0.188485 0.068137 2.766 0.00605 **
Eat 0.048151 0.062137 0.775 0.43905
Media 0.149613 0.063931 2.340 0.01998 *
Automaticity -0.010791 0.007131 -1.513 0.13135
Routine 0.018795 0.006463 2.908 0.00393 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.9303 on 278 degrees of freedom
Multiple R-squared: 0.1529, Adjusted R-squared: 0.1346
F-statistic: 8.363 on 6 and 278 DF, p-value: 2.401e-08
# Model comparisonanova(model_exp2_compulsivity, model_exp2_compulsivity_habit)
Analysis of Variance Table
Model 1: Comp. ~ Impuls. + Stress + Eat + Media
Model 2: Comp. ~ Impuls. + Stress + Eat + Media + Automaticity + Routine
Res.Df RSS Df Sum of Sq F Pr(>F)
1 280 248.34
2 278 240.58 2 7.7646 4.4862 0.01209 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Replication of Experiment 1 to Experiment 2
Additional analysis conducted with subset of questionnaires used in both Experiments 1 and 2 to address Reviewer 2’s comments. This analysis can be found in the supporting information.
Experiment 1
Since the PMPUQ is not present in Experiment 2, the first step is to get the factor structure of the network without the PMPUQ for Experiment 1.
Extract factors from subscales
# Select subscalesvar.subscales <-c("CESD_depressed","CESD_positive","CESD_somatic","CESD_relationship","EAT26_oral_control","EAT26_dieting","EAT26_bulimia","IAT_salience","IAT_excessive_use","IAT_neglect_work","IAT_anticipation","IAT_lack_control","IAT_neglect_social_life","OCIR_Washing","OCIR_checking","OCIR_ordering","OCIR_obsessing","OCIR_hoarding","OCIR_neutralising","PSS_total")db.efa.exp1 <- experiment_1_items[var.subscales]db.efa.descr1 = psych::describe(db.efa.exp1)table_exp1_efa_descr <- knitr::kable(db.efa.descr1 , "html", caption ="Descriptive values for subscales used in Experiment 1") %>% kableExtra::kable_styling(latex_options ="HOLD_position", position ="center", full_width = F) %>%row_spec(0,bold=T,align='c')table_exp1_efa_descr
Descriptive values for subscales used in Experiment 1
Adding cutoff values to questionnaire distributions
Experiment 1
# Labelslabels <-c(CESD_total ="CES-D", COHS_total ="COHS",EAT26_total ="EAT", IAT_total ="IAT", PSS_total ="PSS",OCIR_total ="OCI", UPPS_total ="UPPS",STAIT_total ="STAI-T",PMPUQSV_total ="PMPUQ")cutoff_values <-tribble(~questionnaire, ~cutoff,# CES-D# Morin, A. J. S., Moullec, G., Maïano, C., Layet, L., Just, J.-L., & Ninot, # G. (2011). Psychometric properties of the Center for Epidemiologic Studies # Depression Scale (CES-D) in French clinical and nonclinical adults. Revue # d’Épidémiologie et de Santé Publique, 59(5), 327–340.# https://doi.org/10.1016/j.respe.2011.03.061"CESD_total", 19,# EAT# Leichner, P., Steiger, H., & Gottheil, N. (1994). Validation d’une échelle# d’attitudes alimentaires auprès d’une population québécoise francophone. # 39(1)."EAT26_total", 20,# IAT# Khazaal, Y., Billieux, J., Thorens, G., Khan, R., Louati, Y., Scarlatti,# E., Theintz, F., Lederrey, J., Van Der Linden, M., & Zullino, D. (2008). # French Validation of the Internet Addiction Test. CyberPsychology & # Behavior, 11(6), 703–706. https://doi.org/10.1089/cpb.2007.0249"IAT_total", 50,# OCI-R# Abramowitz, J. S., & Deacon, B. J. (2006). Psychometric properties and # construct validity of the Obsessive–Compulsive Inventory—Revised: # Replication and extension with a clinical sample. Journal of Anxiety # Disorders, 20(8), 1016–1035. https://doi.org/10.1016/j.janxdis.2006.03.001"OCIR_total", 14,# PMPUQ# No cutoff score exists# Harris, B., Regan, T., Schueler, J., & Fields, S. A. (2020). Problematic # Mobile Phone and Smartphone Use Scales: A Systematic Review. Frontiers in # Psychology, 11. https://doi.org/10.3389/fpsyg.2020.00672# PSS# No cutoff score exists# We could use the normative data from the French PSS-10# STAI# Wiglusz, M. S., Landowski, J., & Cubała, W. J. (2019). Psychometric # properties and diagnostic utility of the State–Trait Anxiety Inventory in# epilepsy with and without comorbid anxiety disorder. Epilepsy & Behavior, # 92, 221–225. https://doi.org/10.1016/j.yebeh.2019.01.005"STAIT_total", 52# UPPS# No cutoff score exists)# Plot questionnaire distributionspp <-ggplot(data = experiment_1_questionnaires, aes (x = score, fill = questionnaire)) +facet_wrap(~ questionnaire,scales ="free",labeller =labeller(questionnaire = labels) ) +geom_histogram(aes(y=..density..), alpha=0.6) +geom_density(aes(color = questionnaire), alpha =0.3) +geom_vline(data = cutoff_values, mapping =aes(xintercept = cutoff),linetype ="dashed") +scale_fill_viridis_d(name ="Questionnaires", begin = .1, end = .9,option ="inferno",aesthetics =c("color", "fill"),labels = labels) +theme_bw() +labs(title ="",x ="Experiment 1 questionnaires",y ="Frequency" )# Plot formattingppp_1 <- pp +theme_bw(base_size =10, base_family ="Helvetica") +theme(strip.text.x =element_text(size =10),panel.grid.major =element_blank(),panel.grid.minor =element_blank(),strip.background =element_rect(color ="white", fill="white", linetype ="solid"),axis.ticks.x =element_blank(),axis.text.x =element_blank(),axis.title.x =element_text(size =13, margin =margin(103)),axis.title.y =element_text(size =13),legend.position ="none"# plot.margin = margin(5.5, 5.5, 90, 5.5) )ppp_1
Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
ℹ Please use `after_stat(density)` instead.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Experiment 2
Manual coding
# Khazaal, Y., Chatton, A., Rothen, S., Achab, S., Thorens, G., Zullino, D.,# & Gmel, G. (2016). Psychometric properties of the 7-item game addiction scale # among french and German speaking adults. BMC Psychiatry, 16(1), 132. # https://doi.org/10.1186/s12888-016-0836-3# In accordance with the hypothesis of Lemmens et al. [44], those who scored # “sometimes” or more on all seven items were defined as monothetic gamers # (“pathological gaming”), and those who scored “sometimes” or more on at least # half of the items (four to six of seven items) were defined as polythetic # gamers (excessive gaming).gas <- experiment_2_items %>%select(starts_with("GAS")) %>%mutate(excessive_1 =case_when(`GAS[1]`>=3~1,.default =0 ) ) %>%mutate(excessive_2 =case_when(`GAS[2]`>=3~1,.default =0 ) ) %>%mutate(excessive_3 =case_when(`GAS[3]`>=3~1,.default =0 ) ) %>%mutate(excessive_4 =case_when(`GAS[4]`>=3~1,.default =0 ) ) %>%mutate(excessive_5 =case_when(`GAS[5]`>=3~1,.default =0 ) ) %>%mutate(excessive_6 =case_when(`GAS[6]`>=3~1,.default =0 ) ) %>%mutate(excessive_7 =case_when(`GAS[7]`>=3~1,.default =0 ) ) %>%mutate(excessive_total = excessive_1 + excessive_2 + excessive_3 + excessive_4 + excessive_5 + excessive_6 + excessive_7 ) %>%mutate(excessive =case_when( excessive_total >=4~1,.default =0 ) )# Get number of excessive gamersn_excessive <- gas$excessive %>% plyr::count() %>%filter(x ==1) %>%select(freq)# Calculate cutoff that will result in the correct proportion of individuals# being classified on the plotcutoff_gas <-sort(gas$GAS_total) %>%nth(., (nrow(gas) -as.integer(n_excessive)))
# Hausenblas, H. A., & Downs, D. S. (2002). How Much is Too Much? The # Development and Validation of the Exercise Dependence Scale. Psychology & # Health, 17(4), 387–404. https://doi.org/10.1080/0887044022000004894# Individuals who indicate strong endorsement (i.e., 5 or 6 on the Likert scale)# on at least three of the seven criteria are classified as at-risk.eds <- experiment_2_items %>%select(starts_with("EDSR_")) %>%mutate(tolerance =case_when( EDSR_tolerance >=15~1,.default =0 ) ) %>%mutate(withdrawal =case_when( EDSR_withdrawal >=15~1,.default =0 ) ) %>%mutate(lack_control =case_when( EDSR_lack_control >=15~1,.default =0 ) ) %>%mutate(time =case_when( EDSR_time >=15~1,.default =0 ) ) %>%mutate(reduction_activities =case_when( EDSR_reduction_activities >=15~1,.default =0 ) ) %>%mutate(intention =case_when( EDSR_intention >=15~1,.default =0 ) ) %>%mutate(continuance =case_when( EDSR_continuance >=15~1,.default =0 ) ) %>%mutate(at_risk_total = tolerance + withdrawal + lack_control + time + reduction_activities + intention + continuance ) %>%mutate(at_risk =case_when( at_risk_total >=3~1,.default =0 ) )# Get number of individuals at risk for exercise dependencen_at_risk <- eds$at_risk %>% plyr::count() %>%filter(x ==1) %>%select(freq)# Calculate cutoff that will result in the correct proportion of individuals# being classified on the plotcutoff_eds <-sort(eds$EDSR_total) %>%nth(., (nrow(eds) -as.integer(n_at_risk)))
# Brunault, P., Berthoz, S., Gearhardt, A. N., Gierski, F., Kaladjian, A., # Bertin, E., Tchernof, A., Biertho, L., De Luca, A., Hankard, R., Courtois, # R., Ballon, N., Benzerouk, F., & Bégin, C. (2020). The Modified Yale Food # Addiction Scale 2.0: Validation Among Non-Clinical and Clinical # French-Speaking Samples and Comparison With the Full Yale Food Addiction # Scale 2.0. Frontiers in Psychiatry, 11, 480671. # https://doi.org/10.3389/fpsyt.2020.480671# https://sites.lsa.umich.edu/fastlab/yale-food-addiction-scale/# Mild Food Addiction = 2 or 3 symptoms and clinical significanceyfas <- experiment_2_items %>%select(starts_with("YFAS")) %>%mutate(addiction =case_when( YFAS_score >=2& YFAS_clinical_sign ==1~1,.default =0 ) )# Get number of excessive gamersn_addiction <- yfas$addiction %>% plyr::count() %>%filter(x ==1) %>%select(freq)# Calculate cutoff that will result in the correct proportion of individuals# being classified on the plotcutoff_yfas <-sort(yfas$YFAS_score) %>%nth(., (nrow(eds) -as.integer(n_addiction)))
# Labelslabels <-c(EAT26_total ="EAT", COHS_total ="COHS",PSS_total ="PSS",IAT_total ="IAT", PCLS_total ="PCLS", OCIR_total ="OCI", STICSAT_total ="STICSA-T",UPPS_total ="UPPS",SASSV_total ="SASSV" ,GAS_total ="GAS",EDSR_total ="EDS",LSAS_total ="LSAS",YFAS_score ="mYFAS",QABB_total ="QABB",CESD_total ="CES-D")cutoff_values <-tribble(~questionnaire, ~cutoff,# CES-D# Morin, A. J. S., Moullec, G., Maïano, C., Layet, L., Just, J.-L., & Ninot, # G. (2011). Psychometric properties of the Center for Epidemiologic Studies # Depression Scale (CES-D) in French clinical and nonclinical adults. Revue # d’Épidémiologie et de Santé Publique, 59(5), 327–340.# https://doi.org/10.1016/j.respe.2011.03.061"CESD_total", 19,# EAT# Leichner, P., Steiger, H., & Gottheil, N. (1994). Validation d’une échelle# d’attitudes alimentaires auprès d’une population québécoise francophone. # 39(1)."EAT26_total", 20,# IAT# Khazaal, Y., Billieux, J., Thorens, G., Khan, R., Louati, Y., Scarlatti,# E., Theintz, F., Lederrey, J., Van Der Linden, M., & Zullino, D. (2008). # French Validation of the Internet Addiction Test. CyberPsychology & # Behavior, 11(6), 703–706. https://doi.org/10.1089/cpb.2007.0249"IAT_total", 50,# OCI-R# Abramowitz, J. S., & Deacon, B. J. (2006). Psychometric properties and # construct validity of the Obsessive–Compulsive Inventory—Revised: # Replication and extension with a clinical sample. Journal of Anxiety # Disorders, 20(8), 1016–1035. https://doi.org/10.1016/j.janxdis.2006.03.001"OCIR_total", 14,# PMPUQ# No cutoff score exists# Harris, B., Regan, T., Schueler, J., & Fields, S. A. (2020). Problematic # Mobile Phone and Smartphone Use Scales: A Systematic Review. Frontiers in # Psychology, 11. https://doi.org/10.3389/fpsyg.2020.00672# PSS# No cutoff score exists# We could use the normative data from the French PSS-10# UPPS# No cutoff score exists# EDS-R# No cutoff score, but calculation to determine if at-risk of dependence"EDSR_total", cutoff_eds,# GAS# No cutoff score, but calculation to determine if excessive above"GAS_total", cutoff_gas,# LSAS# Caballo, V. E., Salazar, I. C., Arias, V., Hofmann, S. G., & Curtiss, J. # (2018). Psychometric properties of the Liebowitz Social Anxiety Scale in a # large cross-cultural Spanish and Portuguese speaking sample. Brazilian # Journal of Psychiatry, 41, 122–130. # https://doi.org/10.1590/1516-4446-2018-0006"LSAS_total", 60,# PCLS# Blanchard, E. B., Jones-Alexander, J., Buckley, T. C., & Forneris, # C. A. (1996). Psychometric properties of the PTSD checklist (PCL). Behaviour# Research and Therapy, 34(8), 669–673.# https://doi.org/10.1016/0005-7967(96)00033-2"PCLS_total", 44,# QABB# Lejoyeux, M., Mathieu, K., Embouazza, H., Huet, F., & Lequen, V. (2007). # Prevalence of compulsive buying among customers of a Parisian general store.# Comprehensive Psychiatry, 48(1), 42–46. # https://doi.org/10.1016/j.comppsych.2006.05.005"QABB_total", 10,# SASSV# Lopez-Fernandez, O. (2017). Short version of the Smartphone Addiction Scale # adapted to Spanish and French: Towards a cross-cultural research in # problematic mobile phone use. Addictive Behaviors, 64, 275–280. # https://doi.org/10.1016/j.addbeh.2015.11.013"SASSV_total", 32,# STICSA-T# Van Dam, N. T., Gros, D. F., Earleywine, M., & Antony, M. M. (2013). # Establishing a trait anxiety threshold that signals likelihood of anxiety # disorders. Anxiety, Stress, & Coping, 26(1), 70–86. # https://doi.org/10.1080/10615806.2011.631525"STICSAT_total", 43,# YFAS# No cutoff score, but calculation to determine if addiction present above"YFAS_score", cutoff_yfas)# Plot questionnaire distributionspp <-ggplot(data = experiment_2_questionnaires, aes (x = score, fill = questionnaire)) +facet_wrap(~ questionnaire,scales ="free",labeller =labeller(questionnaire = labels) ) +geom_histogram(aes(y=..density..), alpha=0.6) +geom_density(aes(color = questionnaire), alpha =0.3) +geom_vline(data = cutoff_values, mapping =aes(xintercept = cutoff),linetype ="dashed") +scale_fill_viridis_d(name ="Questionnaires", begin = .1, end = .9,option ="inferno",aesthetics =c("color", "fill"),labels = labels) +theme_bw() +labs(title ="",x ="Experiment 2 questionnaires",y ="" )# Plot formattingppp_2 <- pp +theme_bw(base_size =10, base_family ="Helvetica") +theme(strip.text.x =element_text(size =10),panel.grid.major =element_blank(),panel.grid.minor =element_blank(),strip.background =element_rect(color ="white", fill ="white", linetype ="solid"),axis.ticks.x =element_blank(),axis.text.x =element_blank(),axis.title.x =element_text(size =13),axis.title.y =element_text(size =13),legend.position ="none" )ppp_2
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Create joint figure
p <-ggarrange( ppp_1, ppp_2, labels =c("A", "B"),widths =c(1, 1.3) )
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.